A dataset distillation method combining data-level residual connections, mixed precision, and multi-resolution optimization achieves new state-of-the-art accuracy with roughly half the compute.
Dataset distillation by matching training trajectories
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation
A dataset distillation method combining data-level residual connections, mixed precision, and multi-resolution optimization achieves new state-of-the-art accuracy with roughly half the compute.